{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DIZJS7MCJNJA6HYLWNQM3DQZZ4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56287ddf81849f8b7cd85d8d88260db65387699cfe612f7b86e42571d7b58bfe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T13:17:30Z","title_canon_sha256":"3b68384ae46d0848ac04bd6c35b0f38b48015662990a620c4fb47a2e2c5d90c5"},"schema_version":"1.0","source":{"id":"2608.03632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03632","created_at":"2026-08-05T01:36:47Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03632v1","created_at":"2026-08-05T01:36:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03632","created_at":"2026-08-05T01:36:47Z"},{"alias_kind":"pith_short_12","alias_value":"DIZJS7MCJNJA","created_at":"2026-08-05T01:36:47Z"},{"alias_kind":"pith_short_16","alias_value":"DIZJS7MCJNJA6HYL","created_at":"2026-08-05T01:36:47Z"},{"alias_kind":"pith_short_8","alias_value":"DIZJS7MC","created_at":"2026-08-05T01:36:47Z"}],"graph_snapshots":[{"event_id":"sha256:c82cf04a65917366fc0e2e0bf5508e7c69dded582fe0acc664cca422979d5ec9","target":"graph","created_at":"2026-08-05T01:36:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.03632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense token-level teacher signals. Recent selective OPD methods improve this process by prioritizing signals that are confident, informative, or learnable. However, the assumptions overlook a fundamental failure mode of language models: their token-level judgments can be driven by input-agnostic language priors, formatting conventions, or stereotyped reasoning templates rather than task-specific evidence. We refer to such optimization-relevant but weakly input-grounded supervision as sp","authors_text":"Huajun Chen, Qiang Zhang, Tiankai Li, Xiang Zhuang, Yinuo Jiang, YongJie Ye, Zhou Tao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T13:17:30Z","title":"When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03632","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f52bdb65d6de47b7802400eee9589f0ca4bdaaed9c93b883be55f0bff5a9ba3","target":"record","created_at":"2026-08-05T01:36:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56287ddf81849f8b7cd85d8d88260db65387699cfe612f7b86e42571d7b58bfe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T13:17:30Z","title_canon_sha256":"3b68384ae46d0848ac04bd6c35b0f38b48015662990a620c4fb47a2e2c5d90c5"},"schema_version":"1.0","source":{"id":"2608.03632","kind":"arxiv","version":1}},"canonical_sha256":"1a32997d824b520f1f0bb360cd8e19cf27f8777c44f30ad723ee8da2f7f10d0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a32997d824b520f1f0bb360cd8e19cf27f8777c44f30ad723ee8da2f7f10d0d","first_computed_at":"2026-08-05T01:36:47.573739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:36:47.573739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XPOOk+ENWl0yZA2L+PlNNJd7I5lDvD/C82l9jhVHHz2CFxdSigZ3QrCuS1kosLokjA3omb0STCtXXWfqeTDnDw==","signature_status":"signed_v1","signed_at":"2026-08-05T01:36:47.575225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f52bdb65d6de47b7802400eee9589f0ca4bdaaed9c93b883be55f0bff5a9ba3","sha256:c82cf04a65917366fc0e2e0bf5508e7c69dded582fe0acc664cca422979d5ec9"],"state_sha256":"14e141c35705d338f0bcdc151ec77532ad5fc97ff80a3d16e9b5ca0e1f46a503"}